looot

Preview what a guardrail would exclude

guardrails_preview

Read-onlyIdempotent

looot: preview what a guardrail would exclude, before it is saved: how many of the catalog's providers and endpoints, which jobs would be left with no provider, a reason with a source link for each excluded provider, how many facts are unknown, and how many runs in the last 7 days it would have blocked. Changes nothing. Owners and admins only. Same answer as POST /v1/guardrails/preview.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "settings": "<settings>"
    },
    "name": "guardrails_preview"
  }
}

Input Schema

Name	Required	Description	Default
`subject`	No
`settings`	Yes
`guardrailId`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4.1/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds that it 'Changes nothing', that access is restricted to 'Owners and admins only', and detailed disclosure of what the response contains, including the 7-day lookback window for blocked runs. That is exactly the extra context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and the dense output enumeration is packed into one readable sentence. The leading 'looot:' token is unexplained noise that costs a bit of polish.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return behavior and permission requirements are well covered, which is important given there is no output schema. However, an agent still has no guidance on how to populate settings, subject, or guardrailId, which is a meaningful gap for a tool with a nested-object schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three parameters, including a nested settings object with several enums and the optional guardrailId/subject fields, yet the description never explains any of them. Only 'how many facts are unknown' loosely gestures at the unknownFacts setting, leaving most inputs undocumented in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('preview what a guardrail would exclude') and then enumerates the exact outputs: provider/endpoint counts, jobs left with no provider, per-provider reasons with source links, unknown-fact counts, and blocked runs in the last 7 days. No sibling tool covers guardrails, so there is no ambiguity to resolve.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'before it is saved' clearly places the tool in the workflow, and 'Same answer as POST /v1/guardrails/preview' tells the agent an equivalent HTTP path exists. It stops short of explicit when-not guidance, but for a preview/dry-run tool the timing cue is strong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All looot tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?